通过知识图谱基础增强小型语言模型推理
Enhancing Small Language Models Reasoning through Knowledge Graph Grounding
浏览论文内容
中文总结 AI 辅助
研究利用神经符号智能框架增强小型语言模型推理能力，通过特定工具调用转变模型，在两种场景下评估，发现虽提示提升性能，但受提取瓶颈等限制，还存在“干扰效应”，刻画了挑战并提供迭代验证路线图。
中文摘要 AI 辅助
尽管大型语言模型在零样本推理方面设定了基准，但部署成本高昂且对环境要求高。小型语言模型是可持续替代方案，但在复杂多跳逻辑基础任务中容易出错。我们研究了一种神经符号智能框架，使用CLUTRR亲属关系基准来增强小型语言模型（特别是Gemma 3（1B、4B）和Llama 3.2（3B））的推理能力。我们的方法通过两个专门的工具调用将小型语言模型转变为极简智能体：用于符号三元组提取的extract_facts和通过关系图卷积网络进行专家推理的get_hint。我们在两种配置下评估这些模型，一种是使用真实三元组的预言场景，另一种是依赖自提取知识的现实场景。结果表明，虽然基于关系图卷积网络的提示比仅基于故事的基线性能提高了1.5至2倍，但系统受到提取瓶颈和顺序演绎脆弱性的限制，早期提取错误在多跳链中会加剧。此外，我们在特定架构中发现了“干扰效应”，即尽管有专家提示，但嘈杂的自生成事实会降低性能。这项工作描述了低资源智能系统中符号基础的挑战，并为神经符号智能管道中的迭代验证提供了路线图。
英文摘要
Although large language models (LLMs) have set benchmarks for zero-shot reasoning, their deployment remains cost-prohibitive and environmentally taxing. Small Language Models (SLMs) offer a sustainable alternative, but prone to errors, on tasks requiring complex, multi-hop logical grounding. We investigate a neuro-symbolic agentic framework to enhance the reasoning capabilities of SLMs, specifically Gemma 3 (1B, 4B) and Llama 3.2 (3B), using the CLUTRR kinship benchmark. Our approach transforms the SLM into a minimalist agent utilizing two specialized tool calls: extract_facts for symbolic triplet extraction and get_hint for expert reasoning via a Relational Graph Convolutional Network (RGCN). We evaluate these models across two configurations, both in an Oracle scenario with ground-truth triplets and a Realistic scenario relying on self-extracted knowledge. Our results reveal that while RGCN-derived hints provide a 1.5 - 2x performance gain over story-only baselines, the system is constrained by the extraction bottleneck and sequential deductive fragility, where early extraction errors compound over multi-hop chains. Furthermore, we identify a "distraction effect" in specific architectures where noisy, self-generated facts degrade performance despite the presence of expert hints. This work characterizes the challenges of symbolic grounding in low-resource agentic systems and provides a roadmap for iterative verification in neuro-symbolic agentic pipelines.
发表机构
- Institute of Informatics and Telecommunications, National Center for Scientific Research “Demokritos（信息与电信研究所，国家科学研究中心“德谟克利特”）
机构由 AI 辅助整理，请以论文原文为准。
